This function takes as input a project and returns the corresponding
phenotype table. If the user supplies sample_ids, then the phenotype
table will be subsetted to those ids.
find_samples(project, sample_ids = NULL)
| project | A character vector of length 1.
Valid options are: |
|---|---|
| sample_ids | By default the full phenotype table is returned. The user
can supply a character vector of sample ids (typically LIBD RNA numbers such
as |
A DataFrame-class object with the phenotype table
for the given project. Output can be used in the libd_rse.
## Subset the first two samples from BrainSEQ Phase I find_samples('bsp1', sample_ids = c('R2799', 'R2809'))#> DataFrame with 2 rows and 67 columns #> RNum BrNum Region RIN Age Sex #> <character> <character> <character> <numeric> <numeric> <character> #> R2799 R2799 Br1197 DLPFC 8.4 21.840433 M #> R2809 R2809 Br1245 DLPFC 7.9 42.624028 M #> Race Dx SAMPLE_ID FQCbasicStats perBaseQual #> <character> <character> <CharacterList> <CharacterList> <CharacterList> #> R2799 CAUC Bipolar R2799_C0JYLACXX PASS FAIL #> R2809 CAUC Schizo R2809_D2A01ACXX PASS PASS #> perTileQual perSeqQual perBaseContent GCcontent #> <CharacterList> <CharacterList> <CharacterList> <CharacterList> #> R2799 WARN/FAIL PASS FAIL PASS #> R2809 PASS PASS WARN WARN #> Ncontent SeqLengthDist SeqDuplication OverrepSeqs #> <CharacterList> <CharacterList> <CharacterList> <CharacterList> #> R2799 PASS PASS FAIL/WARN PASS #> R2809 PASS/WARN PASS FAIL PASS #> AdapterContent KmerContent SeqLength_R1 percentGC_R1 phred20.21_R1 #> <CharacterList> <CharacterList> <IntegerList> <IntegerList> <NumericList> #> R2799 PASS FAIL 100 49 38 #> R2809 PASS FAIL 100 47 40 #> phred48.49_R1 phred76.77_R1 phred100_R1 phredGT30_R1 #> <NumericList> <NumericList> <NumericList> <NumericList> #> R2799 36 31 24 0.656484218539493 #> R2809 40 34.5 32 0.926266447639032 #> phredGT35_R1 Adapter50.51_R1 Adapter70.71_R1 Adapter88_R1 #> <NumericList> <NumericList> <NumericList> <NumericList> #> R2799 0.402606866892709 0.274446735976933 0.34763515474898 0.465147635643079 #> R2809 0.761714416330939 0.0562325324565277 0.0731546924482436 0.118039040198923 #> SeqLength_R2 percentGC_R2 phred20.21_R2 phred48.49_R2 phred76.77_R2 #> <IntegerList> <IntegerList> <NumericList> <NumericList> <NumericList> #> R2799 100 49 38 36 33 #> R2809 100 47 40 39 35 #> phred100_R2 phredGT30_R2 phredGT35_R2 Adapter50.51_R2 #> <NumericList> <NumericList> <NumericList> <NumericList> #> R2799 25 0.61804735116388 0.379082599346615 0.295031868940981 #> R2809 32 0.856248317693894 0.657797231213979 0.0597478293398095 #> Adapter70.71_R2 Adapter88_R2 #> <NumericList> <NumericList> #> R2799 0.382246202829382 0.508998289218168 #> R2809 0.0794013186727738 0.118550825070519 #> bamFile #> <CharacterList> #> R2799 /dcl01/ajaffe/data/lab/brainseq_phase1/preprocessed_data/HISAT2_out/R2799_C0JYLACXX_accepted_hits.sorted.bam #> R2809 /dcl01/ajaffe/data/lab/brainseq_phase1/preprocessed_data/HISAT2_out/R2809_D2A01ACXX_accepted_hits.sorted.bam #> trimmed numReads numMapped numUnmapped overallMapRate #> <LogicalList> <IntegerList> <IntegerList> <IntegerList> <NumericList> #> R2799 FALSE 147441360 126030726 21410634 0.8548 #> R2809 FALSE 147327528 139736578 7590950 0.9485 #> concordMapRate totalMapped mitoMapped mitoRate #> <NumericList> <IntegerList> <IntegerList> <NumericList> #> R2799 0.7923 109183563 24087218 0.180738927312207 #> R2809 0.9033 118274615 32205618 0.214018926990896 #> totalAssignedGene gene_Assigned gene_Unassigned_Ambiguity #> <NumericList> <IntegerList> <IntegerList> #> R2799 0.786930346008069 55947123 3707625 #> R2809 0.757340150310627 59327435 3398051 #> gene_Unassigned_MultiMapping gene_Unassigned_NoFeatures #> <IntegerList> <IntegerList> #> R2799 6836188 4604458 #> R2809 9383985 6227106 #> gene_Unassigned_Unmapped gene_Unassigned_MappingQuality #> <IntegerList> <IntegerList> #> R2799 0 0 #> R2809 0 0 #> gene_Unassigned_FragmentLength gene_Unassigned_Chimera #> <IntegerList> <IntegerList> #> R2799 0 0 #> R2809 0 0 #> gene_Unassigned_Secondary gene_Unassigned_Nonjunction #> <IntegerList> <IntegerList> #> R2799 0 0 #> R2809 0 0 #> gene_Unassigned_Duplicate rRNA_rate #> <IntegerList> <NumericList> #> R2799 0 5.3979540645906e-06 #> R2809 0 7.60187929918089e-06 #> bigwig_path #> <CharacterList> #> R2799 /dcl01/ajaffe/data/lab/brainseq_phase1/preprocessed_data/Coverage/R2799_C0JYLACXX.bw #> R2809 /dcl01/ajaffe/data/lab/brainseq_phase1/preprocessed_data/Coverage/R2809_D2A01ACXX.bw## Subset the first two samples from BrainSEQ Phase II find_samples('bsp2', sample_ids = c('R10424', 'R12195'))#> DataFrame with 2 rows and 79 columns #> SAMPLE_ID FQCbasicStats perBaseQual #> <CharacterList> <CharacterList> <CharacterList> #> R10424 R10424_C4KC9ACXX_TAATGCGC_L00 PASS PASS #> R12195 R12195_C4E9TACXX_CGGCTATG_L00 PASS PASS #> perTileQual perSeqQual perBaseContent GCcontent #> <CharacterList> <CharacterList> <CharacterList> <CharacterList> #> R10424 PASS PASS FAIL/WARN WARN/FAIL #> R12195 WARN PASS FAIL/WARN WARN/FAIL #> Ncontent SeqLengthDist SeqDuplication OverrepSeqs #> <CharacterList> <CharacterList> <CharacterList> <CharacterList> #> R10424 PASS PASS FAIL WARN #> R12195 PASS PASS WARN WARN #> AdapterContent KmerContent percentGC_R1 phred100_R1 #> <CharacterList> <CharacterList> <IntegerList> <NumericList> #> R10424 PASS FAIL 43 33 #> R12195 PASS FAIL 44 34 #> phredGT30_R1 phredGT35_R1 Adapter88_R1 percentGC_R2 #> <NumericList> <NumericList> <NumericList> <IntegerList> #> R10424 0.909087695639853 0.708970145082465 2.74234442228771 43 #> R12195 0.906698288285609 0.70642074635339 1.528805377787 44 #> phred100_R2 phredGT30_R2 phredGT35_R2 Adapter88_R2 #> <NumericList> <NumericList> <NumericList> <NumericList> #> R10424 32 0.861428425268134 0.663018859063129 2.75279721539108 #> R12195 34 0.853310879714613 0.659080309341084 1.54911822156688 #> ERCCsumLogErr #> <NumericList> #> R10424 -110.365792667035 #> R12195 -18.3143733824569 #> bamFile #> <CharacterList> #> R10424 /dcl01/lieber/ajaffe/lab/brainseq_phase2/preprocessed_data/DLPFC_RiboZero/HISAT2_out/R10424_C4KC9ACXX_TAATGCGC_L00_accepted_hits.sorted.bam #> R12195 /dcl01/lieber/ajaffe/lab/brainseq_phase2/preprocessed_data/DLPFC_RiboZero/HISAT2_out/R12195_C4E9TACXX_CGGCTATG_L00_accepted_hits.sorted.bam #> trimmed numReads numMapped numUnmapped overallMapRate #> <LogicalList> <IntegerList> <IntegerList> <IntegerList> <NumericList> #> R10424 FALSE 137207346 125018261 12189085 0.9112 #> R12195 FALSE 186256540 173098203 13158337 0.9294 #> concordMapRate totalMapped mitoMapped mitoRate #> <NumericList> <IntegerList> <IntegerList> <NumericList> #> R10424 0.8586 127414655 2250800 0.0173585169619773 #> R12195 0.8862 179828658 2929274 0.0160281634178264 #> totalAssignedGene rRNA_rate RNum BrNum Region #> <NumericList> <NumericList> <character> <character> <factor> #> R10424 0.360011691217133 5.26367757990158e-05 R10424 Br5168 DLPFC #> R12195 0.40055783013167 7.92850345490864e-05 R12195 Br5073 DLPFC #> RIN Age Sex Race Dx snpPC1 #> <NumericList> <numeric> <factor> <factor> <factor> <numeric> #> R10424 6.7 64.08 M CAUC Control 0.0541862 #> R12195 8.4 62.61 M AA SCZD -0.0255144 #> snpPC2 snpPC3 snpPC4 snpPC5 snpPC6 snpPC7 #> <numeric> <numeric> <numeric> <numeric> <numeric> <numeric> #> R10424 0.00141503 -0.0222983 6.7169e-06 8.66316e-05 -0.00505508 -0.00105689 #> R12195 -0.00401754 0.00553881 -0.000578574 -0.00147552 0.00816687 -0.00528997 #> snpPC8 snpPC9 snpPC10 DLFPC_HIPPO_correlation_geneRpkm #> <numeric> <numeric> <numeric> <numeric> #> R10424 0.00511064 -0.00143876 0.000946483 NA #> R12195 0.00590834 -0.00625297 0.00801729 NA #> DLFPC_HIPPO_correlation_exonRpkm DLFPC_HIPPO_correlation_jxnRp10m #> <numeric> <numeric> #> R10424 NA NA #> R12195 NA NA #> DLFPC_HIPPO_correlation_txTpm mean_mitoRate mean_totalAssignedGene #> <numeric> <numeric> <numeric> #> R10424 NA 0.0173585169619773 0.360011691217133 #> R12195 NA 0.0160281634178264 0.40055783013167 #> mean_rRNA_rate mean_RIN agespline_fetal agespline_birth #> <numeric> <numeric> <numeric> <numeric> #> R10424 5.26367757990158e-05 6.7 0 64.08 #> R12195 7.92850345490864e-05 8.4 0 62.61 #> agespline_infant agespline_child agespline_teen agespline_adult #> <numeric> <numeric> <numeric> <numeric> #> R10424 63.08 54.08 44.08 14.08 #> R12195 61.61 52.61 42.61 12.61 #> protocol analysis_regionspecific_adult #> <character> <logical> #> R10424 RiboZeroGold TRUE #> R12195 RiboZeroGold FALSE #> analysis_regionspecific_prenatal analysis_development #> <logical> <logical> #> R10424 FALSE TRUE #> R12195 FALSE FALSE #> analysis_sczd_casecontrol_dlpfc analysis_sczd_casecontrol_hippo #> <logical> <logical> #> R10424 TRUE FALSE #> R12195 TRUE FALSE #> analysis_sczd_casecontrol_interaction analysis_eqtl_dlpfc #> <logical> <logical> #> R10424 TRUE TRUE #> R12195 TRUE TRUE #> analysis_eqtl_hippo analysis_eqtl_interaction #> <logical> <logical> #> R10424 FALSE TRUE #> R12195 FALSE TRUE #> bigwig_path #> <CharacterList> #> R10424 /dcl01/lieber/ajaffe/lab/brainseq_phase2/preprocessed_data/DLPFC_RiboZero/Coverage/R10424_C4KC9ACXX_TAATGCGC_L00.Forward.bw,/dcl01/lieber/ajaffe/lab/brainseq_phase2/preprocessed_data/DLPFC_RiboZero/Coverage/R10424_C4KC9ACXX_TAATGCGC_L00.Reverse.bw #> R12195 /dcl01/lieber/ajaffe/lab/brainseq_phase2/preprocessed_data/DLPFC_RiboZero/Coverage/R12195_C4E9TACXX_CGGCTATG_L00.Forward.bw,/dcl01/lieber/ajaffe/lab/brainseq_phase2/preprocessed_data/DLPFC_RiboZero/Coverage/R12195_C4E9TACXX_CGGCTATG_L00.Reverse.bw